knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)

#Echo = FALSE --> removes code chunks and only shows output

library(tidyverse)
library(here)
library(sf)
library(tmap)

#to intsall packages --> install.packages('packagename') in console

cmd-shift-enter shortcut for running the current code chunk

Reading in the data

Create a code chunk: command-option-i for creating a code chunk

sf_trees <- read_csv(here("data", "sf_trees", "sf_trees.csv"))

#to see a summary of the dataset say summary(df) in the console

Part 1: wragling and ggplot review

Example 1: Find counts of observations by legal_status and wrangle a bit.

### Method 1: group_by() %>%  summarize()
sf_trees %>% 
  group_by(legal_status) %>% 
  summarize(tree_count = n())
## # A tibble: 10 × 2
##    legal_status                 tree_count
##    <chr>                             <int>
##  1 DPW Maintained                   141725
##  2 Landmark tree                        42
##  3 Permitted Site                    39732
##  4 Planning Code 138.1 required        971
##  5 Private                             163
##  6 Property Tree                       316
##  7 Section 143                         230
##  8 Significant Tree                   1648
##  9 Undocumented                       8106
## 10 <NA>                                 54
### Method 2: different way plus a few new functions
top_5_status <- sf_trees %>% 
  count(legal_status) %>% 
  drop_na(legal_status) %>%  #drop rows containing missing values in the legal_status column, if you leave this empty then it will drop any rows that contain a missing value
  rename(tree_count = n) %>% 
  relocate(tree_count) %>% #moves columns around
  slice_max(tree_count, n = 5) %>% #this is taking the top 5 counts
  arrange(desc(tree_count)) #organize by descending order, 
 

#both of these methods do the same thing!

Make a graph of the top 5 from above

ggplot(data = top_5_status, aes(x= fct_reorder(legal_status, tree_count), y = tree_count)) + #fct_reorder takes the legal status results and reorders them according to smallest to largest tree count
  geom_col(fill = 'darkgreen') + #fill changes the color of the columns
  labs(x = 'Legal Status', y = 'Tree Count') +
  coord_flip() + #flips so columns go from vertical alignment to horizontal alginment
  theme_minimal()

Example 2: Only going to keep observations where legal status is “Permitted Site” and caretaker is “MTA”, and store as permitted_data_df

shift-cmd-c to comment/uncomment quickly

# sf_trees$legal_status %>% unique()
# unique(sf_trees$caretaker)
permitted_data_df <- sf_trees %>% 
  filter(legal_status %in% c('Permitted Site', 'Private') & caretaker %in% "MTA") #the row has to match all of the following arguments (if using a comma, for AND use &, for OR use |)

#remember if you use filter with  == c('a', 'b') it will look for a and then b, so in this case you have to use:
#filter(legal_status %in% c('Permitted Site', 'Private'))

Example 3: Only keep Blackwood Acacia trees, and then only keep columns legal_status, date, latitude, longitude and store as blackwood_acacia_df

blackwood_acacia_df <- sf_trees %>% 
  filter(str_detect(species, "Blackwood Acacia")) %>% #str_detect looks through the strings to see if any of the string is detected (aka  if the string has 'my name is Sophia' you can use str_detect to search only for Sophia)
  select(legal_status, date, lat = latitude, lon = longitude) #also renaming columns

### Make a little graph of locations
ggplot(data = blackwood_acacia_df, aes(x=lon, y=lat)) +
  geom_point(color = 'darkgreen')

Example 4: use tidyr::separate() Using separate to use the :: to separate the common name from the scientific name

sf_trees_sep <- sf_trees %>% 
  separate(species, into = c('spp_scientific', 'spp_common'), sep = " :: ")

#this is separating using the :: and renaming the two columns as listed above

** Example 5** use tidyr::unite()

ex_5 <- sf_trees %>% 
  unite("id_status", tree_id, legal_status, sep = "_COOL_")

#this is uniting in a new column "id_status"
# it is dropping the columns

Part 2: make some maps

Using sf package and tmap

Step 1: convert the lat/lon to spatial point, using st_as_sf()

#this is converting to a geometry so it knows it is a spatial object
blackwood_acacia_sf <- blackwood_acacia_df %>% 
  drop_na(lat,lon) %>% 
  st_as_sf(coords = c('lon', 'lat'))

### we need to tell R what the coordinate reference is
st_crs(blackwood_acacia_sf) <-4326 #this is the WGS ESG 84 (classic)

ggplot(data = blackwood_acacia_sf) +
  geom_sf(color = "darkgreen") +
  theme_minimal()

Read in the SF shapefile and add to map

sf_map <- read_sf(here("data", "sf_map", "tl_2017_06075_roads.shp"))

sf_map_transform <- st_transform(sf_map,4326)

ggplot(data = sf_map_transform) +
  geom_sf()

Lets combine the maps!

ggplot() +
  geom_sf(data = sf_map,
          size = 0.1,
          color = 'darkgrey')+
  geom_sf(data = blackwood_acacia_sf, 
          color = 'red',
          size = 0.5) +
  theme_void() +
  labs(title = "blackwood acacias in SF")

Now an interactive map!

tmap_mode('view')

tm_shape(blackwood_acacia_sf) +
  tm_dots()